Abstract

Not too long ago, it was considered state of the art research making a computer distinguish cats vs dogs. Now image classification is the 'Hello World' of Machine Learning (ML) -- something one can implement in just a few lines of code using TensorFlow. In fact, the field of ML has advanced so much in just a few short years that today it is possible to build a potentially life saving, or lethal, application with equal ease. Thus it has become necessary to discuss both the use and abuse of the technology with the hope that we can find ways to mitigate or safeguard against the abuse.

Is it possible to figure out what someone is typing, just by listening to the keystrokes? As one can imagine, it has some serious security implications, e.g., hacking passwords. So I worked on a Machine Learning project called 'kido' (= keystroke decode) to explore this idea and I will present my findings.

Biography

Tikeswar Naik has a Mechanical Engineering degree (PhD in Aerospace), and lately has been drawn towards Machine Learning and exploring its power. He loves building products that can bring positive and lasting impact to people's lives; and, he is working on some ideas towards that.

Lightning Talks

1. "Maps with interactive Folium MarkerClusters on Repl.it and the Matplotlib Basemap toolkit on Google Collaboratory" - Jim Salsman